Writing Draft — LangGraph

Draft a clear first pass from notes — then stop for human edit. No fake claims or invented metrics. (LangGraph stateful graph with a human checkpoint.)

Id: langgraph/writing-draft · Slug: writing-draft · Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

What is this

Code for LangGraph. Draft a clear first pass from notes — then stop for human edit. No fake claims or invented metrics. (LangGraph stateful graph with a human checkpoint.)

How this runtime fits

This LangGraph implementation is a graph-style runtime for the parent AI Team. Agent orchestration and multi-agent workflow language fit when nodes split work and gates; it is not automatically identical to every multi-agent system.

Parent AI Team: writing-draft · What is an AI Team?

What it does

Draft a clear first pass from notes — then stop for human edit. No fake claims or invented metrics. (LangGraph stateful graph with a human checkpoint.)

Who for

Builders working on Content jobs who can run LangGraph themselves.

Need to run

You will run this locally or on infra you control.
No production credentials in prompts or committed files.
Python 3.10+
LangGraph in a venv
Local model binder

How to use

Install LangGraph in a venv (pin versions).
Wire produce() to your local model client.
Run the file once with Example in.
Keep human_gate approval defaulting to False; enable revise only intentionally.

Limitations

Not a substitute for professional legal, medical, or investment advice.
Outputs can be wrong; human review required before publish or spend.
Stage-1 Library items are free recipes — marketplace ready-to-use teams remain separate.
Do not attach billing cloud LLM nodes without a human budget check.

Test status

Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

Files

graph_writing_draft.py — LangGraph nodes + interrupt
README.md — Run notes

Full prompt / config / code

# graph_writing_draft.py — Writing Draft (LangGraph sketch)
# pip install langgraph langchain-core (pin yourself)
# Use a local chat model binder; do not embed secrets.

from typing import TypedDict, Literal
from langgraph.graph import StateGraph, END

SYSTEM = """You are a first-draft writer. Goal: clear prose from notes — then stop.

RULES:
- Do not invent quotes, customers, metrics, or legal claims.
- Mark gaps as [NEED FACT].
- Keep tone plain. Prefer short paragraphs.
- One draft only; wait for human edit directions.

OUTPUT:
1) Working title
2) Draft body
3) [NEED FACT] list
4) Suggested next edit pass"""

class State(TypedDict):
    user_input: str
    draft: str
    approved: bool
    notes: str

def produce(state: State) -> State:
    # Pseudo: call your local model with SYSTEM + state["user_input"]
    draft = "[MODEL OUTPUT PLACEHOLDER — wire your local LLM here]\n" + state["user_input"][:500]
    return {**state, "draft": draft, "notes": "awaiting human"}

def human_gate(state: State) -> State:
    # In real use: interrupt / input() / UI approval.
    # Default False so nothing auto-publishes.
    return {**state, "approved": False}

def route_after_gate(state: State) -> Literal["done", "revise"]:
    return "done" if state.get("approved") else "done"  # stage-1: always end after gate

g = StateGraph(State)
g.add_node("produce", produce)
g.add_node("human_gate", human_gate)
g.set_entry_point("produce")
g.add_edge("produce", "human_gate")
g.add_conditional_edges("human_gate", route_after_gate, {"done": END, "revise": "produce"})
app = g.compile()

if __name__ == "__main__":
    out = app.invoke({"user_input": "PASTE_EXAMPLE_IN", "draft": "", "approved": False, "notes": ""})
    print(out)

Example in

Notes: announce Build Library stage 1. Free. Local AI. Not replacing marketplace teams. Soft CTA to sell/fork.
Audience: AI builders

Example out

Title: Build Library stage 1 is on the shelf
Draft: BotShelf Vampire now has a free Build Library for local AI users…
[NEED FACT]: exact item count at publish
Next edit: tighten CTA; keep marketplace distinction.

Model / runtime notes

Graph includes an explicit human checkpoint. Stage-1 ends after gate (no infinite revise loop).

Canonical Team

Parent: writing-draft · implementation_id: langgraph/writing-draft

GitHub source

teams/writing-draft/langgraph · commit eb87e8e049fdf9908e438305ff827c7b617505b5 · license: free-use-at-own-risk

Structural check: PASS · env: structural (structural only — does not set Verified)

Related Library items

Related marketplace Team pages

Soft thematic links only — not identity merges. Marketplace Teams ≠ Library AI Team records.

Use Write (marketplace Team page — separate entity)
GPT Draft (marketplace Team page — separate entity)